← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
746.7
PP tok/s
57.7
TG tok/s
5486
TTFT (ms)
36.3
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
64 GB
GPU Cores
38
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 726.4 | 61.3 | 36.2 GB | view |
| 4k | 746.7 | 57.7 | 36.3 GB | current |
| 8k | 733.7 | 53.2 | 36.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.3 | 1.00× |
| 2× | 101.4 | 1.65× |
| 4× | 148.8 | 2.43× |
| 8× | 165.6 | 2.70× |